From ef637398a8c2060e15de438020c53331da8bd6dd Mon Sep 17 00:00:00 2001 From: Gunes Bayir Date: Mon, 12 Feb 2024 21:32:51 +0000 Subject: Integrate new pretranspose_b_array with extra fused transpose of B This patch fuses the transposition taking place in Acl with the transformations done in arm_gemm (called pretranspose_b_array) if the underlying kernel and transform supports it. This should improve start-up time (as it's for constant Rhs matrices) and memory footprint. The transformations in arm_gemm are kernel specific. The Rhs matrix is transformed into certain layouts to improve the performance. Resolves: COMPMID-6595 Change-Id: Id2932dd966e59f903c279417bebcea83d9a42464 Signed-off-by: Gunes Bayir Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11144 Tested-by: Arm Jenkins Reviewed-by: Viet-Hoa Do Comments-Addressed: Arm Jenkins Benchmark: Arm Jenkins --- filelist.json | 1 + 1 file changed, 1 insertion(+) (limited to 'filelist.json') diff --git a/filelist.json b/filelist.json index dcf3204ecd..d44a7216ac 100644 --- a/filelist.json +++ b/filelist.json @@ -1592,6 +1592,7 @@ "src/core/NEON/kernels/arm_gemm/gemm_quint8.cpp", "src/core/NEON/kernels/arm_gemm/gemm_uint16.cpp", "src/core/NEON/kernels/arm_gemm/gemm_uint8.cpp", + "src/core/NEON/kernels/arm_gemm/interleave-8way.cpp", "src/core/NEON/kernels/arm_gemm/interleave_indirect.cpp", "src/core/NEON/kernels/arm_gemm/mergeresults-fp16.cpp", "src/core/NEON/kernels/arm_gemm/mergeresults.cpp", -- cgit v1.2.1